INDEX

Explanations

expressions related to being deeply involved or immersed in a situation or environment

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-0.88

awsze

-0.46

 initComponents

-0.44

 AssemblyCompany

-0.44

ametro

-0.43

++)

-0.43

 كومونز

-0.42

Bardzo

-0.42

 Resmi

-0.42

jws

-0.41

POSITIVE LOGITS

 pylab

0.77

 pymysql

0.68

 strass

0.67

 conflic

0.66

 ritard

0.66

 newArr

0.65

 sacerd

0.65

 piacevole

0.65

 FFFF

0.65

 calvin

0.65

Activations Density 0.273%

expressions related to being deeply involved or immersed in a situation or environment

No Comments

No Known Activations